© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 25629
    Prev
    Next
    INDEX
    Explanations

    Summer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    èĹģ
    -0.29
     PEN
    -0.27
    aptic
    -0.26
     actu
    -0.24
     stereo
    -0.24
    _lit
    -0.24
    apes
    -0.24
    bsites
    -0.24
    resse
    -0.23
    çĬ¶æĢģä¸ĭ
    -0.23
    POSITIVE LOGITS
    ç§ģ
    0.26
     Emp
    0.26
    ething
    0.25
     Emperor
    0.24
    管çIJĨå±Ģ
    0.24
    åĪĽä¼¤
    0.23
     ruth
    0.23
     Lik
    0.23
    ä¸¥æł¼æĮīçħ§
    0.23
     Recommended
    0.23
    Activations Density 0.050%

    No Known Activations